{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:56JM66TSAHIQDZDOQ5462BMYQZ","short_pith_number":"pith:56JM66TS","schema_version":"1.0","canonical_sha256":"ef92cf7a7201d101e46e8779ed0598867ab3f47ee7750c8164783bb0773d561b","source":{"kind":"arxiv","id":"2111.00400","version":1},"attestation_state":"computed","paper":{"title":"FANS: Fusing ASR and NLU for on-device SLU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ariya Rastrow, Athanasios Mouchtaris, Martin Radfar, Siegfried Kunzmann","submitted_at":"2021-10-31T03:50:19Z","abstract_excerpt":"Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.00400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T03:50:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8b2f8d08dedd9ca60580dd00fda6c109146206809f1b4a22914b09bd8385c461","abstract_canon_sha256":"aa3081661e3405abe7e8371784aed3c31126b1ef7738d72769485b84145899f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:42.288561Z","signature_b64":"lYYH149f1RgEr/S34nCWIdjhpzoGdLf34JEiWZllZ4kL2kwkF6PJNQLXFVIRQ5qw4LQaq0RA9Y004oAVYRV6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef92cf7a7201d101e46e8779ed0598867ab3f47ee7750c8164783bb0773d561b","last_reissued_at":"2026-07-05T03:27:42.288060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:42.288060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FANS: Fusing ASR and NLU for on-device SLU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ariya Rastrow, Athanasios Mouchtaris, Martin Radfar, Siegfried Kunzmann","submitted_at":"2021-10-31T03:50:19Z","abstract_excerpt":"Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00400","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.00400/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.00400","created_at":"2026-07-05T03:27:42.288114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00400v1","created_at":"2026-07-05T03:27:42.288114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00400","created_at":"2026-07-05T03:27:42.288114+00:00"},{"alias_kind":"pith_short_12","alias_value":"56JM66TSAHIQ","created_at":"2026-07-05T03:27:42.288114+00:00"},{"alias_kind":"pith_short_16","alias_value":"56JM66TSAHIQDZDO","created_at":"2026-07-05T03:27:42.288114+00:00"},{"alias_kind":"pith_short_8","alias_value":"56JM66TS","created_at":"2026-07-05T03:27:42.288114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ","json":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ.json","graph_json":"https://pith.science/api/pith-number/56JM66TSAHIQDZDOQ5462BMYQZ/graph.json","events_json":"https://pith.science/api/pith-number/56JM66TSAHIQDZDOQ5462BMYQZ/events.json","paper":"https://pith.science/paper/56JM66TS"},"agent_actions":{"view_html":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ","download_json":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ.json","view_paper":"https://pith.science/paper/56JM66TS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00400&json=true","fetch_graph":"https://pith.science/api/pith-number/56JM66TSAHIQDZDOQ5462BMYQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/56JM66TSAHIQDZDOQ5462BMYQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ/action/storage_attestation","attest_author":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ/action/author_attestation","sign_citation":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ/action/citation_signature","submit_replication":"https://pith.science/pith/56JM66TSAHIQDZDOQ5462BMYQZ/action/replication_record"}},"created_at":"2026-07-05T03:27:42.288114+00:00","updated_at":"2026-07-05T03:27:42.288114+00:00"}